Artificial Intelligence in agriculture.

Artificial Intelligence (AI) is becoming an important technology in modern agriculture to improve crop productivity, reduce losses, and support sustainable farming practices. This research focuses on developing an intelligent agricultural system that integrates advanced deep learning and machine learning models for crop disease detection, monitoring, yield prediction, and resource optimization. The proposed system uses YOLOv8 and YOLOv9 models to identify and monitor crop diseases through image-based object detection. These models help in detecting plant infections at an early stage and support farmers in taking suitable preventive actions. For crop yield prediction, various machine learning and deep learning algorithms such as Random Forest, Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Convolutional Neural Networks (CNN) are used to analyze agricultural and environmental data. These models learn complex patterns from historical crop data and improve the accuracy of yield estimation. In addition, the Gemini API is integrated into the system to provide intelligent suggestions for water usage, fertilizer application, and crop management. This enables efficient resource utilization and supports sustainable agriculture. The proposed approach combines image analysis, data-driven prediction, and smart recommendation in a single platform. This system reduces manual effort, improves decision-making, and enhances overall farm management. The study contributes to the development of scalable and efficient agricultural solutions that can support farmers, improve food production, and encourage environmentally responsible practices.

Keywords: Artificial Intelligence, Agriculture, YOLOv8, YOLOv9, Crop Disease Detection, Yield Prediction, Random Forest, SVM, CNN, Precision Agriculture.